In order to reduce average arterial vehicle delay, a novel distributed and coordinated traffic control algorithm is developed using the multiple agent system and the reinforce learning （RL）. The RL is used to minimize average delay of arterial vehicles by training the interaction ability between agents and exterior environments. The Robertson platoon dispersion model is embedded in the RL algorithm to precisely predict platoon movements on arteries and then the reward function is developed based on the dispersion model and delay equations cited by HCM2000. The performance of the algorithm is evaluated in a Matlab environment and comparisons between the algorithm and the conventional coordination algorithm are conducted in three different traffic load scenarios. Results show that the proposed algorithm outperforms the conventional algorithm in all the scenarios. Moreover, with the increase in saturation degree, the performance is improved more significantly. The results verify the feasibility and efficiency of the established algorithm.
To satisfy the multiple priority requests from buses that arrive at different phases within a small time window, a multi-phase bus signal priority （MPBSP） strategy is developed. The proximity principle is brought forward to settle the conflicts among multiple priority requests and arrange the optimal priority sequence. To avoid over saturation of the intersection, a conditional MPBSP algorithm that adopts early green and green extension strategies is developed to give priority to the bus with the highest priority level when green time that each phase runs makes its saturation degree not larger than 0. 95. Finally, the algorithm is tested in the VISSIM environment and compared with the normal signal timing algorithm. Sensitive analysis of the number of priority phases, bus demand, and volume to capacity ratios are conducted to quantify their impacts on the benefits of the MPBSP. Results show that the MPBSP strategy can effectively reduce bus delays, and with the increase in the number of priority phases, the reduction range of bus delays also increases.
